Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4541 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1176812 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1777. Min Act: -0.0002

Data Index: 385654 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1608. Min Act: -0.0002

Data Index: 1002019 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1527. Min Act: -0.0002

Data Index: 904941 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1578. Min Act: -0.0002

Data Index: 1241921 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1564. Min Act: -0.0002

Data Index: 1013888 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1480. Min Act: -0.0002

Data Index: 423873 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1530. Min Act: -0.0002

Data Index: 342301 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1529. Min Act: -0.0002

Data Index: 1036752 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1529. Min Act: -0.0002

Data Index: 914081 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1540. Min Act: -0.0002

Data Index: 499243 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1444. Min Act: -0.0002

Data Index: 548616 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1398. Min Act: -0.0002

Data Index: 1155339 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1560. Min Act: -0.0002

Data Index: 1259020 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1503. Min Act: -0.0002

Data Index: 567973 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1496. Min Act: -0.0002

Data Index: 1045184 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1491. Min Act: -0.0002

Data Index: 138238 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1054534 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1305. Min Act: -0.0002

Data Index: 815597 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1212355 (C4 (Web Text))

Max Activating Token Index: 348